Code Interpreter
Adds secure code execution capabilities to Claude Desktop using E2B Sandbox, supporting both JavaScript and Python environments.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Code Interpreter, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
MCP server that runs agent-generated code inside E2B's secure cloud sandboxes. It executes arbitrary code in isolated microVMs, which is the central capability and the central risk (sandbox escape, resource abuse).
Key features and capabilities
- Run arbitrary code in a sandbox
- Isolated cloud microVMs
- Stdout/stderr capture
Use cases
- Safe code execution for agents
- Data-analysis scripting